scientific-brainstorming
No security findings. Scanned 1 time, most recently 2026-10-21.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs. Use for early-stage research brainstorming or prioritizing candidate directions; hand off empirical validation, study design, ethics or regulatory review, and clinical questions to appropriate experts or skills.
- Package
- 10 files, 133 KB
- SKILL.md
- 1753 words, 12+ sections
- Code
- Python (4)
- License
- MIT
- Compatibility
- Core guidance works in any Agent Skills-compatible host. Optional bundled CLIs require Python 3.11+ and use only the standard library; they make no network or LLM calls and require no credentials.
SKILL.md covers: Scientific Brainstorming · Purpose and boundaries · Operating rules · Reproducible workflow · 1. Scope the session · 2. Diversify perspectives deliberately · 3. Generate independently · 4. Share without immediate evaluation · 5. Cluster structurally · 6. Define transparent criteria · 7. Run adversarial review · 8. Check literature and evidence
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 14 KB |
references/brainstorming_methods.md | doc | 12 KB |
references/facilitation_workflows.md | doc | 9.8 KB |
references/idea_evaluation.md | doc | 12 KB |
references/responsible_ai.md | doc | 10 KB |
references/sources.md | doc | 17 KB |
scripts/_common.py | script | 9.7 KB |
scripts/evaluate_matrix.py | script | 20 KB |
scripts/session_scaffold.py | script | 7.7 KB |
scripts/validate_register.py | script | 20 KB |
External hosts referenced
pubmed.ncbi.nlm.nih.gov www.cos.io doi.org arxiv.org grants.nih.gov www.science.org www.sciencedirect.com allea.org efsa.onlinelibrary.wiley.com export.arxiv.org link.springer.com orwh.od.nih.gov pmc.ncbi.nlm.nih.gov psycnet.apa.org research-and-innovation.ec.europa.eu research.rug.nl www.aspr.gov www.icmje.org www.nature.com www.rand.org www.tandfonline.com www.unesco.org www.who.int
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22 at commit 593377bb0487. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/K-Dense-AI/scientific-agent-skills
- Raw scan result: skills-scientific-brainstorming-scan.json
- Badge for your README:
- Request a re-scan